How can we customize the source code for changing the input activations of the layers?

Intel® Distribution of OpenVINO™ Toolkit

Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

How can we customize the source code for changing the input activations of the layers?

514 Views

We are working on exploring optimization techniques for which intermediate activations needs to be modified. But we are facing some issues in finding the specific file from where we can tap the input activation values for the intermediate layers and change them according to our requirements. In a previous post, I found a way to get the intermediate tensors. But how can we change the values before feeding to the next layer?

https://software.intel.com/en-us/forums/computer-vision/topic/804937#comment-1948406

Link Copied

0 Replies

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.